Agents

Deep

• A2C
• DDPG
• DQN
• PPO1
• VPG
• TD3
• SAC

Classical

• Q-Learning
• SARSA

Bandit

• Contextual Bandit
  • Base
  • Bootstrap Neural
  • Fixed
  • Linear Posterior
  • Neural Greedy
  • Neural Linear Posterior
  • Neural Noise Sampling
  • Variational
• Multi-Armed Bandit
  • Base
  • Bayesian Bandit
  • Bernoulli Bandit
  • Espilon Greedy
  • Gaussian
  • Gradient
  • Thmopson Sampling
  • Upper Confidence Bound